INDEX

Explanations

-H

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åģľçĶµ

-0.27

 pillars

-0.26

 moons

-0.25

ToFront

-0.25

leon

-0.25

æĺİäº®

-0.25

.setColumns

-0.24

 lenses

-0.24

getWindow

-0.24

ç©

-0.24

POSITIVE LOGITS

cmc

0.30

ware

0.27

Pt

0.26

 profes

0.25

orgen

0.25

åĩºä¼ļ

0.24

äº¤ä»£

0.24

æİº

0.24

gm

0.24

å·¥ä¸ļåĮĸ

0.23

Activations Density 0.085%

-H

No Comments

No Known Activations